Document Type


Publication Date



link prediction, social networks, academic networks


The prediction of new relationships in a social network is a complex and extremely useful task to enhance or maximize collaborations by indicating what the most promising partnerships are. In academic social networks, prediction of relationships is typically used to try to identify potential partners in the development of a project and/or co-authors for publishing papers. This paper presents a system that combines artificial intelligence techniques with the state-of-the-art metrics for link prediction. The resulting system was tested using real data from Computer Science researchers and achieved a precision above 99.5% in the co-authorship prediction.


This paper is in Portuguese (Um Sistema de Predição de Relacionamentos em Redes Sociais)